用大模型改进向量伪相关反馈，提升密集检索效果。
LLM-VPRF: Large Language Model Based Vector Pseudo Relevance Feedback
- 用大模型生成查询向量的迭代反馈，优化检索
- 在多个数据集上验证，大模型下仍显著提升性能
- 适合研究密集检索与大模型融合的学者
向量伪相关反馈（VPRF）通过迭代优化查询表示，在基于BERT的密集检索系统中展现出良好效果。本文探究VPRF在大语言模型（LLM）驱动的密集检索器中的泛化能力。我们提出LLM-VPRF，并在多个基准数据集上评估其有效性，分析不同LLM对反馈机制的影响。结果表明，VPRF的优势可成功延伸至LLM架构，证明其是一种鲁棒的增强密集检索性能的技术，无论底层模型如何。本工作弥合了传统BERT基密集检索与现代LLM之间的差距，为未来方向提供洞察。
原文摘要 · Abstract (English)
Vector Pseudo Relevance Feedback (VPRF) has shown promising results in improving BERT-based dense retrieval systems through iterative refinement of query representations. This paper investigates the generalizability of VPRF to Large Language Model (LLM) based dense retrievers. We introduce LLM-VPRF and evaluate its effectiveness across multiple benchmark datasets, analyzing how different LLMs impact the feedback mechanism. Our results demonstrate that VPRF's benefits successfully extend to LLM architectures, establishing it as a robust technique for enhancing dense retrieval performance regardless of the underlying models. This work bridges the gap between VPRF with traditional BERT-based dense retrievers and modern LLMs, while providing insights into their future directions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。